test_tokenization_t5.py

# coding=utf-8
# Copyright 2018 Google T5 Authors and HuggingFace Inc. team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from __future__ import absolute_import, division, print_function, unicode_literals

import os

from transformers.tokenization_t5 import T5Tokenizer
from transformers.tokenization_xlnet import SPIECE_UNDERLINE

from .tokenization_tests_commons import CommonTestCases


SAMPLE_VOCAB = os.path.join(os.path.dirname(os.path.abspath(__file__)), "fixtures/test_sentencepiece.model")


class T5TokenizationTest(CommonTestCases.CommonTokenizerTester):

    tokenizer_class = T5Tokenizer

    def setUp(self):
        super(T5TokenizationTest, self).setUp()

        # We have a SentencePiece fixture for testing
        tokenizer = T5Tokenizer(SAMPLE_VOCAB)
        tokenizer.save_pretrained(self.tmpdirname)

    def get_tokenizer(self, **kwargs):
        return T5Tokenizer.from_pretrained(self.tmpdirname, **kwargs)

    def get_input_output_texts(self):
        input_text = "This is a test"
        output_text = "This is a test"
        return input_text, output_text

    def test_full_tokenizer(self):
        tokenizer = T5Tokenizer(SAMPLE_VOCAB)

        tokens = tokenizer.tokenize("This is a test")
        self.assertListEqual(tokens, ["▁This", "▁is", "▁a", "▁t", "est"])

        self.assertListEqual(tokenizer.convert_tokens_to_ids(tokens), [285, 46, 10, 170, 382])

        tokens = tokenizer.tokenize("I was born in 92000, and this is falsé.")
        self.assertListEqual(
            tokens,
            [
                SPIECE_UNDERLINE + "I",
                SPIECE_UNDERLINE + "was",
                SPIECE_UNDERLINE + "b",
                "or",
                "n",
                SPIECE_UNDERLINE + "in",
                SPIECE_UNDERLINE + "",
                "9",
                "2",
                "0",
                "0",
                "0",
                ",",
                SPIECE_UNDERLINE + "and",
                SPIECE_UNDERLINE + "this",
                SPIECE_UNDERLINE + "is",
                SPIECE_UNDERLINE + "f",
                "al",
                "s",
                "é",
                ".",
            ],
        )
        ids = tokenizer.convert_tokens_to_ids(tokens)
        self.assertListEqual(ids, [8, 21, 84, 55, 24, 19, 7, 0, 602, 347, 347, 347, 3, 12, 66, 46, 72, 80, 6, 0, 4])

        back_tokens = tokenizer.convert_ids_to_tokens(ids)
        self.assertListEqual(
            back_tokens,
            [
                SPIECE_UNDERLINE + "I",
                SPIECE_UNDERLINE + "was",
                SPIECE_UNDERLINE + "b",
                "or",
                "n",
                SPIECE_UNDERLINE + "in",
                SPIECE_UNDERLINE + "",
                "<unk>",
                "2",
                "0",
                "0",
                "0",
                ",",
                SPIECE_UNDERLINE + "and",
                SPIECE_UNDERLINE + "this",
                SPIECE_UNDERLINE + "is",
                SPIECE_UNDERLINE + "f",
                "al",
                "s",
                "<unk>",
                ".",
            ],
        )